Initial upload: distiluse-base-multilingual-cased-v2 XNNPACK fp32 for RNE v0.9.0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+xnnpack/distiluse-base-multilingual-cased-v2_xnnpack_fp32.pte filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,33 @@
+---
+license: apache-2.0
+---
+
+# Introduction
+
+This repository hosts the [distiluse-base-multilingual-cased-v2](https://huggingface.co/sentence-transformers/distiluse-base-multilingual-cased-v2/tree/main) model for the [React Native ExecuTorch](https://www.npmjs.com/package/react-native-executorch) library. It includes the model exported for xnnpack in `.pte` format, ready for use in the **ExecuTorch** runtime.
+
+If you'd like to run this model in your own ExecuTorch runtime, refer to the [official documentation](https://pytorch.org/executorch/stable/index.html) for setup instructions.
+
+## Compatibility
+
+If you intend to use this model outside of React Native ExecuTorch, make sure your runtime is compatible with the **ExecuTorch** version used to export the `.pte` files. For more details, see the compatibility note in the [ExecuTorch GitHub repository](https://github.com/pytorch/executorch/blob/11d1742fdeddcf05bc30a6cfac321d2a2e3b6768/runtime/COMPATIBILITY.md?plain=1#L4). If you work with React Native ExecuTorch, the constants from the library will guarantee compatibility with the runtime used behind the scenes.
+
+This model was exported using React Native ExecuTorch `v0.9.0`, which ships an ExecuTorch runtime derived from the `v1.2.0` release branch. **No forward compatibility** is guaranteed — older versions of the runtime may not work with these files.
+
+## Repository Structure
+
+- `xnnpack/distiluse-base-multilingual-cased-v2_xnnpack_fp32.pte` — ExecuTorch program partitioned for the XNNPACK delegate, fp32. Wire this to the `modelSource` argument.
+- `tokenizer.json` — HuggingFace fast-tokenizer dump (WordPiece + BertNormalizer). Wire this to `tokenizerSource`.
+- `config.json`, `tokenizer_config.json` — upstream model/tokenizer configs, kept for reference and for non-RNE consumers.
+
+## Model details
+
+- Architecture: DistilBERT multilingual cased + mean pooling + Dense (768→512, Tanh) + L2 norm.
+- Output dimension: **512**.
+- Max sequence length: **126** tokens (128 − 2 for `[CLS]` / `[SEP]`).
+- Languages: 50+ (multilingual).
+- Typical strength: cross-lingual sentence similarity and medium-length sentence retrieval. Short single-word queries in non-English languages are this model's weakest case — for those, longer sentences and/or English inputs give markedly better ranking.
+
+## Export notes
+
+The exported program skips HuggingFace's internal attention-mask-to-4D conversion because the RNE runtime never pads at inference (single sentence, no batching). This preserves bit-exactness with the PyTorch reference (RMSE 0 on fp32 random input) while trimming ~27% off the forward wall-time and keeping XNNPACK delegation around 89–91% of graph runtime.

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "old_models/distiluse-base-multilingual-cased-v2/0_DistilBERT",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertModel"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.7.0",
+  "vocab_size": 119547
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/home/reimers/.cache/torch/sentence_transformers/sbert.net_models_distiluse-base-multilingual-cased/0_DistilBERT/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "old_models/distiluse-base-multilingual-cased-v2/0_DistilBERT", "do_basic_tokenize": true, "never_split": null}

xnnpack/distiluse-base-multilingual-cased-v2_xnnpack_fp32.pte

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb996370e33f8e76b1e597cdab904bf4562dcdd0237efcda41eacadba87a0a0
+size 540641536